python-下载某学习平台视频

---

前言

平台的web端是没有开放下载的，所以我们从网页元素里找到视频链接。
但是平台的音频和视频是分离的，所以要找到两个链接下载到本地，然后进行合并操作后保存。

1、获取视频 url

选择一个普通正常的视频，不需要大会员的那种

2、发送请求

定义一个请求函数，用来获取页面元素

def get_url(url):
    """
    获取网页元素文本
    :param url:
    :return: 返回url页面元素
    """
    head = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62'
    }
    res = requests.get(url=url, headers=head)
    return res

3、数据解析

定义一个函数来获取视频标题，视频画面，音频的链接
video里的backupUrl就是它的视频链接
audio里的backupUrl就是它的音频链接

def get_json_url(url):
    res = get_url(url=url).text
    title = re.findall('<title data-vue-meta="true">(.*?)</title>', res)[0]  # 获取视频标题
    play_info = json.loads(re.findall('<script>window.__playinfo__=(.*?)<script>', res)[0][0:-9])
    audio = play_info['data']['dash']['audio'][0]['backupUrl'][0]
    video = play_info['data']['dash']['video'][0]['backupUrl'][0]
    tit_au_vi = [title, video, audio]
    return tit_au_vi

4、本地保存

定义一个函数，用上面获取的链接来进行下载保存成二进制文件

def save(url):
    json_data = get_json_url(url=url)
    title = json_data[0]
    video_content = get_url(url=json_data[1]).content
    audio_content = get_url(url=json_data[2]).content
    with open(title + '.mp4', mode='wb') as file:
        file.write(video_content)
    with open(title + '.mp3', mode='wb') as file:
        file.write(audio_content)

5、音视频合并

ffmpeg是一款非常好用处理音视频的工具包

pip install ffmpeg

def merge(title):
    audio = ffmpeg.input(f'{title}.mp3')
    video = ffmpeg.input(f'{title}.mp4')
    print("合并视音频")
    out = ffmpeg.output(video, audio, f'E:/material/{title}.mp4')
    out.run()
    os.remove(f'{title}.mp3')
    os.remove(f'{title}.mp4')

5、完整代码

import requests
import json
import re
from pprint import pprint


def get_url(url):
    """
    获取网页元素文本
    :param url:
    :return: 返回url页面元素
    """
    head = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62',
        'referer': 'https://www.**.com/'
    }
    res = requests.get(url=url, headers=head)
    return res


def get_json_url(url):
    """
    获取视频标题  视频画面  音频
    :param url: 视频页面地址
    :return: 返回视频标题 视频画面 音频
    """
    res = get_url(url).text
    title = re.findall('<title data-vue-meta="true">(.*?)</title>', res)[0]  # 获取视频标题
    play_info = json.loads(re.findall('<script>window.__playinfo__=(.*?)<script>', res)[0][0:-9])
    # pprint(play_info)
    video = play_info['data']['dash']['video'][0]['backupUrl'][0]
    audio = play_info['data']['dash']['audio'][0]['backupUrl'][0]
    tit_au_vi = [title, video, audio]
    return tit_au_vi


def save(url):
    """
    :param url:
    :return:
    """
    json_data = get_json_url(url=url)
    title = json_data[0]
    video_content = get_url(url=json_data[1]).content
    audio_content = get_url(url=json_data[2]).content
    with open(f'{title}.mp4', mode='wb') as file:
        file.write(video_content)
    with open(f'{title}.mp3', mode='wb') as file:
        file.write(audio_content)
	merge(title)

def start(bv):
    """
    :param url:
    :return:
    """
    print('开始下载')
    url = f'https://www.**.com/video/{bv}'
    save(url)
    print('下载完成')

def merge(title):
    audio = ffmpeg.input(f'{title}.mp3')
    video = ffmpeg.input(f'{title}.mp4')
    print("合并视音频")
    out = ffmpeg.output(video, audio, f'E:/material/{title}.mp4')
    out.run()
    os.remove(f'{title}.mp3')
    os.remove(f'{title}.mp4')

if __name__ == '__main__':
    start('BV1H341157Tz')